© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5619
    Prev
    Next
    INDEX
    Explanations

    responsive design compatibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mingw
    0.34
    using
    0.33
    ProtectedRoute
    0.33
     oscura
    0.33
    COMPUTER
    0.32
     disadvantaged
    0.30
     Dif
    0.30
    {[
    0.30
     PROTE
    0.29
    逋
    0.29
    POSITIVE LOGITS
    compatibility
    0.37
    icules
    0.35
     compatibility
    0.34
    সত্য
    0.34
     Compat
    0.32
    rvats
    0.32
     Compatibility
    0.32
     rejoice
    0.32
     дета
    0.32
     détaillé
    0.32
    Activations Density 0.012%

    No Known Activations